CtrlK
BlogDocsLog inGet started
Tessl Logo

design-prompt-generator-v2

Advanced 7-step hierarchical design prompt generator for AI web development tools (Lovable, Cursor, Bolt). Generates domain-aware, user-journey-based design prompts with emotional design considerations. Triggers on "디자인 프롬프트", "웹 디자인", "Lovable 프롬프트", "랜딩페이지 만들어줘", or any AI web builder prompt requests.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mostly lean instruction-only skill with clear sequencing, concrete templates, and useful reference tables. Main room for improvement is reducing placeholder density in templates and tightening a few sections.

Suggestions

Replace some [placeholder]-heavy templates with one fully worked example (e.g., a sample filled color system or one complete component spec) to lift actionability from scaffold to copy-paste-ready.

Add a brief validation/review checkpoint between Step 7 and the Output Format (e.g., 're-run the Quality Checklist before emitting the final prompt') to make the workflow feedback loop explicit.

Consider moving the large domain-pattern and emotion-matrix tables into a references/ file referenced from the body, which would shorten SKILL.md and let progressive disclosure reach the top anchor.

DimensionReasoningScore

Conciseness

Mostly lean and efficient — organized as compact tables, templates, and bullet specs without explaining concepts Claude already knows; only minor instances that could be trimmed further.

4 / 5

Actionability

Provides concrete scaffolds (component template, color/typography/spacing specs, output format) plus actionable tables (domain patterns, emotion matrix, micro-interaction categories with recommended durations); templates rely on placeholders but the surrounding guidance is specific and usable.

4 / 5

Workflow Clarity

The 7 steps are explicitly sequenced (Step 1 → Step 7) with a defined Output Format and a closing Quality Checklist acting as a checkpoint; no explicit validation feedback loops, but none are critical for non-destructive prompt generation.

4 / 5

Progressive Disclosure

Single self-contained SKILL.md with well-organized section headers and no need for external bundle files (none present); structure is clear, though the file exceeds the ~50-line simple-skill threshold that would let well-organized sections alone reach 5.

4 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states capability and trigger conditions in third person with concrete Korean trigger phrases. It is slightly abstract on the action list but otherwise well-scoped and distinctive.

DimensionReasoningScore

Specificity

Names the domain (design prompt generator for Lovable/Cursor/Bolt) and several concrete aspects — "domain-aware, user-journey-based design prompts with emotional design considerations" and a "7-step hierarchical" structure — but these are modifiers on a single core action rather than a list of distinct operations, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both "what" (generates domain-aware, user-journey-based design prompts with emotional design considerations) and "when" ("Triggers on ... or any AI web builder prompt requests") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases ("디자인 프롬프트", "웹 디자인", "Lovable 프롬프트", "랜딩페이지 만들어줘") plus tool names and "any AI web builder prompt requests", giving good coverage though a few synonym variations are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (design-prompt generation for specific AI web builders) with distinct Korean trigger phrases and named tools, giving minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bear2u/my-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.